Epileptiform Activity Detection via Wavelet Subband Entropy and Kurtosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting epileptiform activity in brain wave data lack specificity and are unable to distinguish between epileptiform activity and changes in consciousness, requiring high computation power and being unsuitable for ambulatory devices.
Innovation Solution
A mechanism that decomposes brain wave signal data into subbands using wavelet transforms to detect specific epileptiform waveforms by calculating entropy and kurtosis values, allowing for efficient and automatic detection of specific types of epileptiform activity with reduced computational requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods for detecting epileptiform activity are used, then detection capability is achieved, but specificity is poor and inability to distinguish from changes in consciousness occurs
Solution Approach 1:
The EEG signal is decomposed into multiple frequency subbands (delta, theta, alpha, beta, gamma) using wavelet transform. This segmentation allows the detection algorithm to analyze specific frequency components associated with epileptiform activity separately, improving specificity by focusing on relevant frequency ranges while filtering out unrelated brain states.
Solution Approach 2:
The detection method applies different statistical measures (entropy, kurtosis, skewness) to different frequency subbands. By tailoring the analysis approach to each frequency band's characteristics, the system achieves better local detection quality for epileptiform patterns while maintaining reliability in distinguishing them from other brain states.
2Measurement precision
If comprehensive EEG analysis methods are used, then detection accuracy improves, but computation power requirements increase
Solution Approach 1:
Instead of analyzing the entire EEG spectrum with complex algorithms, the method applies statistical measures (entropy, kurtosis, skewness) selectively to specific frequency subbands where epileptiform activity is most likely to occur. This partial action approach maintains detection accuracy while significantly reducing computational requirements.
Solution Approach 2:
The patent replaces complex mechanical signal processing systems with statistical field-based analysis. By using entropy, kurtosis, and skewness calculations on wavelet-decomposed subbands, the system achieves high detection accuracy with minimal computational power, making it suitable for ambulatory devices.
Data Source
AI summary
The invention relates to detection of epileptiform activity. In order to accomplish a mechanism with improved specificity to epileptiform activity and with the capability to detect specific type of epileptic patterns, brain wave signal data obtained from a subject is decomposed into at least one predetermined subband, each subband being indicative of a specific type of epileptiform activity. The subband-specific output data obtained represents a time series of a quantitative characteristic of the brain wave signal data. At least one measure is determined for any one or more of the at least one predetermined subband, the at least one measure belonging to a measure set comprising a first measure indicative of the entropy of the subband-specific output data and a second measure indicative of a normalized form of k:th order central moment of the subband-specific output data, where k is an integer higher than three. The presence of a specific type of epileptiform activity may be detected based on the at least one measure of the respective subband.